From be445759b631ea1ec954d70e8e1f30cfb9271f2b Mon Sep 17 00:00:00 2001 From: sysadminstory Date: Thu, 28 Mar 2024 19:44:27 +0100 Subject: [PATCH] [PepperBridgeAbstract,DealabsBridge,HotUKDealsBridge,MydealsBridge] Move as much as possible to JSON (#4032) As the website use more and more JSON, and JSON is a machine readable format, I migrated as much as possible to the JSON. This simplifies the Abstract class a lot, and the Bridge classes need less language specifi strings. --- bridges/DealabsBridge.php | 42 +---- bridges/HotUKDealsBridge.php | 51 +----- bridges/MydealsBridge.php | 50 +----- bridges/PepperBridgeAbstract.php | 259 ++++++++----------------------- 4 files changed, 69 insertions(+), 333 deletions(-) diff --git a/bridges/DealabsBridge.php b/bridges/DealabsBridge.php index c65f0c75..62d854f6 100644 --- a/bridges/DealabsBridge.php +++ b/bridges/DealabsBridge.php @@ -1915,9 +1915,6 @@ class DealabsBridge extends PepperBridgeAbstract 'thread-error' => 'Impossible de déterminer l\'ID de la discussion. Vérifiez l\'URL que vous avez entré', 'no-results' => 'Aucun résultat', 'currency' => '€', - 'relative-date-indicator' => [ - 'il y a', - ], 'price' => 'Prix', 'shipping' => 'Livraison', 'origin' => 'Origine', @@ -1925,42 +1922,7 @@ class DealabsBridge extends PepperBridgeAbstract 'title-keyword' => 'Recherche', 'title-group' => 'Groupe', 'title-talk' => 'Surveillance Discussion', - 'local-months' => [ - 'janvier', - 'février', - 'mars', - 'avril', - 'mai', - 'juin', - 'juillet', - 'août', - 'septembre', - 'octobre', - 'novembre', - 'décembre' - ], - 'local-time-relative' => [ - 'il y a ', - 'min', - 'h', - 'jour', - 'jours', - 'mois', - 'ans', - 'et ' - ], - 'date-prefixes' => [ - 'Actualisé ', - ], - 'relative-date-alt-prefixes' => [ - 'Actualisé ', - ], - 'relative-date-ignore-suffix' => [ - ], - - 'localdeal' => [ - 'Local', - 'Pays d\'expédition' - ], + 'deal-type' => 'Type de deal', + 'localdeal' => 'Deal Local', ]; } diff --git a/bridges/HotUKDealsBridge.php b/bridges/HotUKDealsBridge.php index 1f059123..b631db73 100644 --- a/bridges/HotUKDealsBridge.php +++ b/bridges/HotUKDealsBridge.php @@ -3279,9 +3279,6 @@ class HotUKDealsBridge extends PepperBridgeAbstract 'thread-error' => 'Unable to determine the thread ID. Check the URL you entered', 'no-results' => 'no results', 'currency' => '£', - 'relative-date-indicator' => [ - 'ago', - ], 'price' => 'Price', 'shipping' => 'Shipping', 'origin' => 'Origin', @@ -3289,51 +3286,7 @@ class HotUKDealsBridge extends PepperBridgeAbstract 'title-keyword' => 'Search', 'title-group' => 'Group', 'title-talk' => 'Discussion Monitoring', - 'local-months' => [ - 'Jan', - 'Feb', - 'Mar', - 'Apr', - 'May', - 'Jun', - 'Jul', - 'Aug', - 'Sep', - 'Occ', - 'Nov', - 'Dec', - 'st', - 'nd', - 'rd', - 'th' - ], - 'local-time-relative' => [ - 'Posted ', - 'm', - 'h,', - 'day', - 'days', - 'month', - 'year', - 'and ' - ], - 'date-prefixes' => [ - 'Posted ', - 'Found ', - 'Refreshed ', - 'Made hot ' - ], - 'relative-date-alt-prefixes' => [ - 'Made hot ', - 'Refreshed ', - 'Last updated ' - ], - 'relative-date-ignore-suffix' => [ - '/by.*$/' - ], - 'localdeal' => [ - 'Local', - 'Expires' - ] + 'deal-type' => 'Deal Type', + 'localdeal' => 'Local deal', ]; } diff --git a/bridges/MydealsBridge.php b/bridges/MydealsBridge.php index 08e32a0c..41bae46c 100644 --- a/bridges/MydealsBridge.php +++ b/bridges/MydealsBridge.php @@ -2026,10 +2026,6 @@ class MydealsBridge extends PepperBridgeAbstract 'thread-error' => 'Die ID der Diskussion kann nicht ermittelt werden. Überprüfen Sie die eingegebene URL', 'no-results' => 'keine Ergebnisse', 'currency' => '€', - 'relative-date-indicator' => [ - 'vor', - 'seit' - ], 'price' => 'Preis', 'shipping' => 'Versand', 'origin' => 'Ursprung', @@ -2037,49 +2033,7 @@ class MydealsBridge extends PepperBridgeAbstract 'title-keyword' => 'Suche', 'title-group' => 'Gruppe', 'title-talk' => 'Überwachung Diskussion', - 'local-months' => [ - 'Jan', - 'Feb', - 'Mär', - 'Apr', - 'Mai', - 'Jun', - 'Jul', - 'Aug', - 'Sep', - 'Okt', - 'Nov', - 'Dez', - '.' - ], - 'local-time-relative' => [ - 'eingestellt vor ', - 'm', - 'h,', - 'day', - 'days', - 'month', - 'year', - 'and ' - ], - 'date-prefixes' => [ - 'eingestellt am ', - 'lokal ', - 'aktualisiert ', - ], - 'relative-date-alt-prefixes' => [ - 'aktualisiert vor ', - 'kommentiert vor ', - 'eingestellt vor ', - 'heiß seit ', - 'vor ' - ], - 'relative-date-ignore-suffix' => [ - '/von.*$/' - ], - 'localdeal' => [ - 'Lokal ', - 'Läuft bis ' - ] + 'deal-type' => 'Angebotsart', + 'localdeal' => 'Lokales Angebot', ]; } diff --git a/bridges/PepperBridgeAbstract.php b/bridges/PepperBridgeAbstract.php index d0e15238..7b40ea1c 100644 --- a/bridges/PepperBridgeAbstract.php +++ b/bridges/PepperBridgeAbstract.php @@ -46,35 +46,6 @@ class PepperBridgeAbstract extends BridgeAbstract $html = getSimpleHTMLDOM($url); $list = $html->find('article[id][class*=thread--deal]]'); - // Deal Image Link CSS Selector - $selectorImageLink = implode( - ' ', /* Notice this is a space! */ - [ - 'cept-thread-image-link', - 'imgFrame', - 'imgFrame--noBorder', - 'thread-listImgCell', - ] - ); - - // Deal Link CSS Selector - $selectorLink = implode( - ' ', /* Notice this is a space! */ - [ - 'cept-tt', - 'thread-link', - 'linkPlain', - ] - ); - - // Deal Hotness CSS Selector - $selectorHot = implode( - ' ', /* Notice this is a space! */ - [ - 'vote-box' - ] - ); - // Deal Description CSS Selector $selectorDescription = implode( ' ', /* Notice this is a space! */ @@ -83,65 +54,39 @@ class PepperBridgeAbstract extends BridgeAbstract ] ); - // Deal Date CSS Selector - $selectorDate = implode( - ' ', /* Notice this is a space! */ - [ - 'size--all-s', - 'flex', - 'boxAlign-jc--all-fe' - ] - ); - // If there is no results, we don't parse the content because it display some random deals $noresult = $html->find('h3[class*=text--b]', 0); if ($noresult != null && strpos($noresult->plaintext, $this->i8n('no-results')) !== false) { $this->items = []; } else { foreach ($list as $deal) { - $item = []; - $item['uri'] = $this->getDealURI($deal); - $item['title'] = $this->getTitle($deal); - $item['author'] = $deal->find('span.thread-username', 0)->plaintext; - // Get the JSON Data stored as vue $jsonDealData = $this->getDealJsonData($deal); + $dealMeta = Json::decode($deal->find('div[class=threadGrid-headerMeta]', 0)->find('div[class=js-vue2]', 1)->getAttribute('data-vue2')); + + $item = []; + $item['uri'] = $this->getDealURI($jsonDealData); + $item['title'] = $this->getTitle($jsonDealData); + $item['author'] = $this->getDealAuthor($jsonDealData); $item['content'] = '
' . $this->getImage($deal) . '' - . $this->getHTMLTitle($item) + . $this->getHTMLTitle($jsonDealData) . $this->getPrice($jsonDealData) . $this->getDiscount($jsonDealData) - . $this->getShipsFrom($deal) - . $this->getShippingCost($deal) + . $this->getShipsFrom($dealMeta) + . $this->getShippingCost($jsonDealData) . $this->getSource($jsonDealData) + . $this->getDealLocation($dealMeta) . $deal->find('div[class*=' . $selectorDescription . ']', 0)->innertext . '' . $this->getTemperature($jsonDealData) . '
'; - // Check if a clock icon is displayed on the deal - $clocks = $deal->find('svg[class*=icon--clock]'); - if ($clocks !== null && count($clocks) > 0) { - // Get the last clock, corresponding to the deal posting date - $clock = end($clocks); - - // Find the text corresponding to the clock - $spanDateDiv = $clock->next_sibling(); - $itemDate = $spanDateDiv->plaintext; - // In some case of a Local deal, there is no date, but we can use - // this case for other reason (like date not in the last field) - if ($this->contains($itemDate, $this->i8n('localdeal'))) { - $item['timestamp'] = time(); - } elseif ($this->contains($itemDate, $this->i8n('relative-date-indicator'))) { - $item['timestamp'] = $this->relativeDateToTimestamp($itemDate); - } else { - $item['timestamp'] = $this->parseDate($itemDate); - } - } + $item['timestamp'] = $this->getPublishedDate($jsonDealData); $this->items[] = $item; } } @@ -284,22 +229,31 @@ HEREDOC; } } + /** + * Get the Publish Date from a Deal if it exists + * @return integer Timestamp of the published date of the deal + */ + private function getPublishedDate($jsonDealData) + { + return $jsonDealData['props']['thread']['publishedAt']; + } + + /** + * Get the Deal Author from a Deal if it exists + * @return String Author of the deal + */ + private function getDealAuthor($jsonDealData) + { + return $jsonDealData['props']['thread']['user']['username']; + } + /** * Get the Title from a Deal if it exists * @return string String of the deal title */ - private function getTitle($deal) + private function getTitle($jsonDealData) { - $titleRoot = $deal->find('div[class*=threadGrid-title]', 0); - $titleA = $titleRoot->find('a[class*=thread-link]', 0); - $titleFirstChild = $titleRoot->first_child(); - if ($titleA !== null) { - $title = $titleA->plaintext; - } else { - // In some case, expired deals have a different format - $title = $titleRoot->find('span', 0)->plaintext; - } - + $title = $jsonDealData['props']['thread']['title']; return $title; } @@ -318,14 +272,10 @@ HEREDOC; * Get the HTML Title code from an item * @return string String of the deal title */ - private function getHTMLTitle($item) + private function getHTMLTitle($jsonDealData) { - if ($item['uri'] == '') { - $html = '

' . $item['title'] . '

'; - } else { - $html = '

' - . $item['title'] . '

'; - } + $html = '

' + . $this->getTitle($jsonDealData) . '

'; return $html; } @@ -334,10 +284,11 @@ HEREDOC; * Get the URI from a Deal if it exists * @return string String of the deal URI */ - private function getDealURI($deal) + private function getDealURI($jsonDealData) { - $dealId = $deal->attr['id']; - $uri = $this->i8n('bridge-uri') . $this->i8n('uri-deal') . str_replace('_', '-', $dealId); + $dealSlug = $jsonDealData['props']['thread']['titleSlug']; + $dealId = $jsonDealData['props']['thread']['threadId']; + $uri = $this->i8n('bridge-uri') . $this->i8n('uri-deal') . $dealSlug . '-' . $dealId; return $uri; } @@ -345,18 +296,14 @@ HEREDOC; * Get the Shipping costs from a Deal if it exists * @return string String of the deal shipping Cost */ - private function getShippingCost($deal) + private function getShippingCost($jsonDealData) { - if ($deal->find('span[class*=space--ml-2 size--all-s overflow--wrap-off]', 0) != null) { - if ($deal->find('span[class*=space--ml-2 size--all-s overflow--wrap-off]', 0)->children(1) != null) { + $isFree = $jsonDealData['props']['thread']['shipping']['isFree']; + $price = $jsonDealData['props']['thread']['shipping']['price']; + if ($isFree !== null) { return '
' . $this->i8n('shipping') . ' : ' - . strip_tags($deal->find('span[class*=space--ml-2 size--all-s overflow--wrap-off]', 0)->children(1)->innertext) + . $price . ' ' . $this->i8n('currency') . '
'; - } else { - return '
' . $this->i8n('shipping') . ' : ' - . strip_tags($deal->find('span[class*=text--color-greyShade flex--inline]', 0)->innertext) - . '
'; - } } else { return ''; } @@ -422,6 +369,25 @@ HEREDOC; } } + /** + * Get the Deal location if it exists + * @return string String of the deal location + */ + private function getDealLocation($dealMeta) + { + $ribbons = $dealMeta['props']['metaRibbons']; + $isLocal = false; + foreach ($ribbons as $ribbon) { + $isLocal |= ($ribbon['type'] == 'local'); + } + if ($isLocal) { + $content = '
' . $this->i8n('deal-type') . ' : ' . $this->i8n('localdeal') . '
'; + } else { + $content = ''; + } + return $content; + } + /** * Get the Picture URL from a Deal if it exists * @return string String of the deal Picture URL @@ -437,9 +403,8 @@ HEREDOC; * Get the originating country from a Deal if it exists * @return string String of the deal originating country */ - private function getShipsFrom($deal) + private function getShipsFrom($dealMeta) { - $dealMeta = Json::decode($deal->find('div[class=threadGrid-headerMeta]', 0)->find('div[class=js-vue2]', 1)->getAttribute('data-vue2')); $metas = $dealMeta['props']['metaRibbons']; $shipsFrom = null; foreach ($metas as $meta) { @@ -453,104 +418,6 @@ HEREDOC; return ''; } - /** - * Transforms a local date into a timestamp - * @return int timestamp of the input date - */ - private function parseDate($string) - { - $month_local = $this->i8n('local-months'); - $month_en = [ - 'January', - 'February', - 'March', - 'April', - 'May', - 'June', - 'July', - 'August', - 'September', - 'October', - 'November', - 'December' - ]; - - // A date can be prfixed with some words, we remove theme - $string = $this->removeDatePrefixes($string); - // We translate the local months name in the english one - $date_str = trim(str_replace($month_local, $month_en, $string)); - - // If the date does not contain any year, we add the current year - if (!preg_match('/[0-9]{4}/', $string)) { - $date_str .= ' ' . date('Y'); - } - - // Add the Hour and minutes - $date_str .= ' 00:00'; - $date = DateTime::createFromFormat('j F Y H:i', $date_str); - // In some case, the date is not recognized : as a workaround the actual date is taken - if ($date === false) { - $date = new DateTime(); - } - return $date->getTimestamp(); - } - - /** - * Remove the prefix of a date if it has one - * @return the date without prefiux - */ - private function removeDatePrefixes($string) - { - $string = str_replace($this->i8n('date-prefixes'), [], $string); - return $string; - } - - /** - * Remove the suffix of a relative date if it has one - * @return the relative date without suffixes - */ - private function removeRelativeDateSuffixes($string) - { - if (count($this->i8n('relative-date-ignore-suffix')) > 0) { - $string = preg_replace($this->i8n('relative-date-ignore-suffix'), '', $string); - } - return $string; - } - - /** - * Transforms a relative local date into a timestamp - * @return int timestamp of the input date - */ - private function relativeDateToTimestamp($str) - { - $date = new DateTime(); - - // The minimal amount of time substracted is a minute : the seconds in the resulting date would be related to the execution time of the script. - // This make no sense, so we set the seconds manually to "00". - $date->setTime($date->format('H'), $date->format('i'), 0); - - // In case of update date, replace it by the regular relative date first word - $str = str_replace($this->i8n('relative-date-alt-prefixes'), $this->i8n('local-time-relative')[0], $str); - - $str = $this->removeRelativeDateSuffixes($str); - - $search = $this->i8n('local-time-relative'); - - $replace = [ - '-', - 'minute', - 'hour', - 'day', - 'month', - 'year', - '' - ]; - $date->modify(str_replace($search, $replace, $str)); - - - return $date->getTimestamp(); - } - /** * Returns the RSS Feed title according to the parameters * @return string the RSS feed Tiyle